Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.5765. Min Act: -0.1700
Data Index: 6824707 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 4116277 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 8514265 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.1702. Min Act: -0.1700
Data Index: 7841265 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.1702. Min Act: -0.1700
Data Index: 2661306 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.1390. Min Act: -0.1700
Data Index: 5392394 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.1077. Min Act: -0.1700
Data Index: 6782656 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.1077. Min Act: -0.1700
Data Index: 345185 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.1077. Min Act: -0.1700
Data Index: 2389337 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.0452. Min Act: -0.1700
Data Index: 1605863 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.0452. Min Act: -0.1700
Data Index: 2715749 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.0140. Min Act: -0.1700
Data Index: 5352343 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9827. Min Act: -0.1700
Data Index: 8777267 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9827. Min Act: -0.1700
Data Index: 4407495 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9827. Min Act: -0.1700
Data Index: 7963137 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9515. Min Act: -0.1700
Data Index: 1228715 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9515. Min Act: -0.1700
Data Index: 3421120 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9515. Min Act: -0.1700
Data Index: 7934123 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9202. Min Act: -0.1700
Data Index: 3122916 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5765. Min Range: -6.5765
Max Act: 5.9202. Min Act: -0.1700
Data Index: 304210 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19